A Video Processing and Machine Learning Based Method for Evaluating Safety-Critical Operator Engagement in a Motorway Control Room

Impact Factor:2.4

DOI number:10.1080/00140139.2023.2223784

Journal:Ergonomics

Place of Publication:英国

Key Words:User experience; control room; engagement evaluation; body posture estimation; artificial intelligence

Abstract:In safety-critical automatic systems, safety can be compromised if operators lack engagement. Effective detection of undesirable engagement states can inform the design of interventions for enhancing engagement. However, the existing engagement measurement methods suffer from several limitations which damage their effectiveness in the work environment. A novel engage- ment evaluation methodology, which adopts Artificial Intelligence (AI) technologies, has been proposed. It was developed using motorway control room operators as subjects. Openpose and Open Source Computer Vision Library (OpenCV) were used to estimate the body postures of operators, then a Support Vector Machine (SVM) was utilised to build the engagement evalu- ation model based on discrete states of operator engagement. The average accuracy of the evaluation results reached 0.89 and the weighted average precision, recall, and F1-score were all above 0.84. This study emphasises the importance of specific data labelling when measuring typical engagement states, forming the basis for potential control room improvements.

First Author:金林轶

Indexed by:SCI

Correspondence Author:金林轶

Discipline:Engineering

Translation or Not:no

Date of Publication:2023-06-25

Included Journals:SCI

Links to published journals:https://www.tandfonline.com/doi/full/10.1080/00140139.2023.2223784